LocalForge
Back to guide
MODEL / OPENAI

gpt-oss-120b

OpenAI targets one 80 GB accelerator. Correct serving requires Harmony format support.

Primary source
Total parameters117B5.1B active / token
Estimated memory~80 GBMXFP4
Context128KText
LicenseApache-2.0Primarily English
01 / BEST FOR
  • reasoning
  • agents
  • datacenter serving
02 / ESTIMATED FIT
03 / DEPLOY WITH
vLLMAdvancedvllm serve openai/gpt-oss-120b --dtype auto
TensorRT-LLMAdvancedtrtllm-serve openai/gpt-oss-120b
llama.cppMediumllama-server -m /path/to/verified-model.gguf --port 8080
Watch out

OpenAI targets one 80 GB accelerator. Correct serving requires Harmony format support.